SWAB-IntEco/confluence-model-test

README.md

@@ -0,0 +1,52 @@
+---
+license: other
+base_model: AI-Sweden-Models/gpt-sw3-126m-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: test_trainer
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test_trainer
+
+This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-126m-instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m-instruct) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "AI-Sweden-Models/gpt-sw3-126m-instruct",
+  "activation_function": "gelu",
+  "apply_query_key_layer_scaling": true,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.023,
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 2048,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "normalize_attention_scores": true,
+  "pad_token_id": 0,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tokenizer_class": "GPTSw3Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8628a176d9a0f56f0fade2c680d697dece1cc6a35c5f7e134110ca1643fa0111
+size 543138432

runs/Dec20_06-58-18_d85ef0b1f8ab/events.out.tfevents.1703055499.d85ef0b1f8ab.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cbaede1a76937e66d082e1385f39e4dc2f8fd42a9b99207c92942b13cf86d7
+size 4864

runs/Dec20_07-01-14_d85ef0b1f8ab/events.out.tfevents.1703055675.d85ef0b1f8ab.228.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4f3bd9a9bb6f3b3cec964c43262bc4db1764e21b596b309787e1110ce87a18
+size 4864

runs/Dec20_07-07-07_d85ef0b1f8ab/events.out.tfevents.1703056028.d85ef0b1f8ab.228.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2080ef70f55ecee95d153f4a5428cb3e1910eb65406b6857b44f55673188c0c7
+size 4864

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa00ea5368283d1435026e2ccef930f81ea9d2ad72160a111a26584ac09d315
+size 4536